Rerun a run from its receipt
A run’s receipt names its command and the commit it ran on. Rerun the command on that commit and record the rerun as a check.
Paste this into your agent
Section titled “Paste this into your agent”Rerun seed 2 from its receipt, on the code it ran on, and check it.
Rerun seed 2 of int8-ptq from its Rabbit Brain receipt, and tell me if it still gives the same numbers. - Run `rb context --model <your model id>` first. - Read the run's receipt with `rb show <run id>`: the command, and the commit it ran on. - Check out that commit in a worktree inside this repository (`git worktree add .worktrees/rerun <commit>`), and run the receipt's command there through `rb journal run`. - Record the new run as a check of the old one: `--repeats <run id> --again --why "rerun from its receipt"`, with `--commit`. Finish with `rb show` of the criterion exactly as printed, and what rb says of the repeat.
Since the runs, one commit changed how eval.py builds its output path.
What you’ll see
Section titled “What you’ll see”$ rb show top1-drop-budgetCriterion top1-drop-budget on int8-ptq (primary, own): INT8 loses at most 0.5 points of top-1 against FP32 top1-drop-budget INT8 loses at most 0.5 points of top-1 against FP32 criterion met · loss · change.top1 ≥ -0.5 (n ≥ 3) reads: change.top1: -0.08 [-0.1545, -0.005476] % · paired difference, t interval, 3 seeds, 95% (rb) result: loss: the interval clear of 0 on the worse side (higher is better) rule: criterion met: estimate -0.08 ≥ -0.5 timing: declared before the evidence (by production times) units: 3 seeds from 4 runs, 1 repeat integrity: ok · runt6sqax repeats runssvuju: the same number, a check that holds rung2qpud: difference -0.11 (file) · unit seed=1 · seed=1 runssvuju: difference -0.08 (file) · unit seed=2 · seed=2 runqllqdf: difference -0.05 (file) · unit seed=3 · seed=3 runt6sqax: difference -0.08 (file) · unit seed=2 · repeats runssvuju · seed=2The rerun is a repeat of seed 2, so the criterion, a rule a result must meet, still rests on 3 seeds: “from 4 runs, 1 repeat”.
What rb did, step by step
Section titled “What rb did, step by step”-
See what a rerun needs
Terminal window $ rb show int8-ptqExperiment int8-ptq: INT8 post-training quantization · open · under q-int8design not confirmed · list it to confirm: rb confirm int8-ptqhypothesis or purpose: not recordedwhy: not recordedvariants: fp32 (baseline) · int8 (candidate)varies: precision, calib_imagesspec 85201d31eae8 · frozen 2026-11-10T15:32:35.679+00:00 (85201d31eae8) · note: before the runs · not confirmedsettings:optim.lr 0.1 verified · configs/train.yaml#optim.lroptim.momentum 0.9 verified · configs/train.yaml#optim.momentumdata.batch_size 128 verified · configs/train.yaml#data.batch_sizeeval.batch_size 256 verified · configs/train.yaml#eval.batch_sizeseed (each run) per-run · no sourcefp32.precision fp32 verified · configs/fp32.yaml#precisionint8.precision int8 verified · configs/int8.yaml#precisionint8.calib_images 512 verified · configs/int8.yaml#calib_imagescriteria:top1-drop-budget INT8 loses at most 0.5 points of top-1 against FP32criterion met · loss · change.top1 ≥ -0.5 (n ≥ 3)reads: change.top1: -0.08 [-0.1545, -0.005476] % · paired difference, t interval, 3 seeds, 95% (rb)result: loss: the interval clear of 0 on the worse side (higher is better)rule: criterion met: estimate -0.08 ≥ -0.5timing: declared before the evidence (by production times)units: 3 seedsintegrity: okruns: rung2qpud, runssvuju, runqllqdfto run it again:code ok commit 12ec61a726fecode · commit 12ec61a726fe, which all 3 runs ran atyour checkout differs in 1 file: eval.pyshow code diff:git diff 12ec61a726feda8c90dbba424b07ee7ec0b9d32c -- ":(top)" ":(top,exclude).rb"rebuild:git worktree add --detach ../int8-ptq-12ec61a 12ec61a726feda8c90dbba424b07ee7ec0b9d32cenvironment ok python 3.14.4files ok all 3 files the runs named are here unchanged -
Read the run’s receipt
Terminal window $ rb show runssvujuRun runssvuju on int8-ptq (file)produced 2026-11-10 15:32 UTC (its file's time) · recorded 2026-11-10 15:32 UTCfp32.top1 = 91.66int8.top1 = 91.58per-run: seed=2command (as given): python eval.py --seed 2 (rb journal run watched it make these numbers, 2026-11-10)code that made it: 12ec61a726fe (as given)your checkout differs in 1 file: eval.pyrepository when recorded: commit 12ec61a726feconfig results/int8-ptq/seed2/config.yaml: 5 match, 0 differ, 0 absentfile results/int8-ptq/seed2/metrics.json sha256 342131bfa92f (72 bytes) · here -
See what changed since
Terminal window $ git diff 12ec61a -- eval.pydiff --git a/eval.py b/eval.pyindex 35a1cb3..901a798 100644--- a/eval.py+++ b/eval.py@@ -7,7 +7,7 @@ p = argparse.ArgumentParser()p.add_argument("--seed", type=int, required=True)a = p.parse_args()fp32, int8 = TOP1[a.seed]-out = f"results/int8-ptq/seed{a.seed}"+out = os.path.join("results", "int8-ptq", f"seed{a.seed}")os.makedirs(out, exist_ok=True)with open(f"{out}/metrics.json", "w") as f:json.dump({"fp32": {"top1": fp32}, "int8": {"top1": int8}}, f, indent=2) -
Check out the receipt’s commit in a worktree
Terminal window $ git worktree add -q .worktrees/rerun 12ec61aThen, in
.worktrees/rerun:Terminal window $ rb context# The record: INT8 ResNet-20 on CIFAR-10This worktree (no branch · ~/int8-rerun/.worktrees/rerun) has no record of its own: rb writes to the record in main · ~/int8-rerun, and each run keeps this worktree's code.… (98 more lines) -
Run the receipt’s command
Terminal window $ rb journal run -- python eval.py --seed 2{"metrics": {"fp32.top1": 91.66, "int8.top1": 91.58}}exit 0. The command, its exit code and what it wrote are in the journal.It printed its metrics: fp32.top1=91.66, int8.top1=91.58. rb reconcile proposes no new run: a recorded run of int8-ptq holds these numbers.Next: rb reconcile -
Record it as a check
The output matches the first run’s byte for byte.
--again --whyrecords it anyway, as a second execution, and--repeatsmakes it a check of seed 2, not a new seed.Terminal window $ rb run add int8-ptq --from results/int8-ptq/seed2/metrics.json --set seed=2 --config results/int8-ptq/seed2/config.yaml --command "python eval.py --seed 2" --commit 12ec61a726feda8c90dbba424b07ee7ec0b9d32c --repeats runssvuju --again --why "rerun from its receipt"runt6sqax on int8-ptq: fp32.top1=91.66, int8.top1=91.58 · seed=2Ran with the spec: 5 of its settings found in .worktrees/rerun/results/int8-ptq/seed2/config.yaml, all matching.It repeats runssvuju: a check of that run, in its unit, never a new one.Produced: 2026-11-10 15:32:38 (file)top1-drop-budget criterion met · loss: change.top1: -0.08 [-0.1545, -0.005476] % · paired difference, t interval, 3 seeds, 95% (rb)Next: rb show top1-drop-budgetTerminal window $ rb show runt6sqaxRun runt6sqax on int8-ptq (file)produced 2026-11-10 15:32 UTC (its file's time) · recorded 2026-11-10 15:32 UTCfp32.top1 = 91.66int8.top1 = 91.58per-run: seed=2command (as given): python eval.py --seed 2 (rb journal run watched it make these numbers, 2026-11-10)code that made it: 12ec61a726fe (as given)your checkout has this coderepository when recorded: commit 12ec61a726feconfig .worktrees/rerun/results/int8-ptq/seed2/config.yaml: 5 match, 0 differ, 0 absentfile .worktrees/rerun/results/int8-ptq/seed2/metrics.json sha256 342131bfa92f (72 bytes) · herenote: recorded again: rerun from its receipt. · not confirmed
Rabbit Brainrabbitbrain.ai · GitHub · PyPI · Privacy · Apache-2.0